Multi-area battery replacement cabinet positioning reminding and planning system and method

Abstract

The invention discloses a multi-area battery replacement cabinet positioning reminding and planning system and method, and relates to the technical field of battery replacement cabinet energy supplement service. Comprising a data acquisition module used for acquiring a user data set, a power conversion cabinet data set and an environment data set in a target service area, and preprocessing the user data set, the power conversion cabinet data set and the environment data set; and the power conversion demand prediction module is used for carrying out comprehensive analysis on the preprocessed user data set and the environment data set to obtain a power conversion demand prediction value, and evaluating the power conversion demand scale and distribution of each region in a future preset time period according to the power conversion demand prediction value. According to the invention, through arrangement of the battery replacement demand prediction module, accurate matching of the battery replacement cabinet with sufficient supply and demand during battery replacement of a user is realized, battery replacement failure caused by battery shortage is avoided, data support is provided for battery reserve planning and regional layout optimization of the battery replacement cabinet, and the battery replacement efficiency is improved. And the waste problems of service interruption of a high-demand area and resource overstock of a low-demand area are avoided.

Description

Technical Field

[0001] This invention relates to the field of battery swapping cabinet energy replenishment service technology, specifically to a multi-area battery swapping cabinet location reminder and planning system and method. Background Technology

[0002] A battery swapping station is an intelligent device that provides rapid battery swapping services for electric vehicles. By storing fully charged batteries and receiving batteries waiting to be charged, it enables users to efficiently replenish energy without having to wait a long time to charge. It is widely used in scenarios such as short-distance urban travel and logistics delivery, and is a core component of the electric vehicle energy replenishment network.

[0003] The planning of battery swapping stations refers to the overall optimization of the layout, battery reserves, operation and maintenance of battery swapping stations based on regional needs and resource distribution. Customer reminders are to push information such as the location, availability, and compatibility of battery swapping stations to users, guiding them to complete the battery swapping efficiently. The two together constitute the core links of the battery swapping service.

[0004] In existing technologies, the accuracy of battery swapping demand forecasting is insufficient, which can easily lead to battery shortages in high-demand areas and resource backlogs in low-demand areas. The recommendation of battery swapping cabinets does not fully integrate multiple key factors, and users often encounter battery swapping failures or poor experiences. There is a lack of solutions that take into account both supply and demand balance and user experience. Therefore, a multi-regional battery swapping cabinet location reminder and planning system and method is proposed to solve these problems. Summary of the Invention

[0005] Technical problems to be solved To address the shortcomings of existing technologies, this invention provides a multi-area battery swapping cabinet positioning reminder and planning system and method, which solves the problems mentioned in the background art.

[0006] Technical solution To achieve the above objectives, the present invention provides the following technical solution: a multi-area battery swapping cabinet positioning reminder and planning system, comprising: The data acquisition module is used to collect user datasets, battery swapping cabinet datasets, and environmental datasets within the target service area, and to preprocess these datasets. The battery swapping demand forecasting module is used to comprehensively analyze the preprocessed user dataset and environmental dataset to obtain the battery swapping demand forecast value, and to evaluate the scale and distribution of battery swapping demand in each region within a preset time period based on the battery swapping demand forecast value. The battery health assessment module is used to comprehensively analyze the preprocessed battery swapping cabinet dataset, obtain battery health prediction values, and evaluate the current performance status of each battery in the battery swapping cabinet based on the battery health prediction values, and select healthy batteries that meet user needs. The load prediction module is used to comprehensively analyze the preprocessed battery swapping cabinet dataset and the predicted battery swapping demand to obtain the regional battery swapping cabinet load prediction value, and to evaluate the idle status and congestion risk of each battery swapping cabinet in the future preset time period based on the regional battery swapping cabinet load prediction value. The distance assessment module is used to comprehensively analyze the user location data in the preprocessed user dataset and the battery swapping cabinet location data in the preprocessed battery swapping cabinet dataset to obtain the distance assessment value, and to assess the convenience of users to reach each battery swapping cabinet based on the distance assessment value. The comprehensive recommendation module is used to perform correlation analysis on the preprocessed user dataset, battery swapping cabinet dataset, and environmental dataset to obtain scenario adaptation factors. It then performs comprehensive analysis on the scenario adaptation factors, battery swapping demand prediction values, battery health prediction values, regional battery swapping cabinet load prediction values, and distance assessment values ​​to obtain battery swapping cabinet recommendation assessment values. Based on the battery swapping cabinet recommendation assessment values, it selects the optimal battery swapping cabinet and alternative battery swapping cabinets from the battery swapping cabinets in each region.

[0007] Preferably, the user dataset includes user location data and user feature data, wherein the user location data includes the user's real-time location coordinates, historical battery swapping location coordinates, and actual travel distance data from the current location to the battery swapping cabinets in each area, and the user feature data includes the user's vehicle model parameters, compatible battery model, current remaining battery power, and range requirements. The battery swapping cabinet dataset includes battery swapping cabinet location data, battery status data, and battery swapping cabinet operation data. The battery swapping cabinet location data includes the geographic coordinates of each battery swapping cabinet and the area information to which it belongs. The battery status data includes voltage time series data, temperature data, battery health, battery rated parameters, and battery charge and discharge cycle count. The battery swapping cabinet operation data includes battery reserve, real-time number of available bays, and real-time load of the battery swapping cabinet. The environmental dataset includes traffic data, which includes real-time congestion index and road travel time.

[0008] Preferably, the specific steps for obtaining the predicted battery swapping demand are as follows: Extract historical battery swapping time, battery swapping potential, and battery swapping frequency data from the preprocessed user dataset, and combine them with historical battery swapping data from the same period in the corresponding time period. The extracted multi-dimensional data is correlated and matched in terms of time and space. Combined with the real-time occupancy status of the battery swapping cabinet, the occupancy adjustment coefficient is set. The battery swapping demand in areas with high occupancy is adjusted upward by the coefficient, and the battery swapping demand in areas with low occupancy is adjusted downward by the coefficient, thus forming a sample of regional battery swapping demand analysis. Based on the analysis of the sample, the influence trend of different dimensions of data on battery swapping demand is analyzed, and the predicted value of battery swapping demand in each region within a preset time period is obtained through multi-dimensional correlation analysis.

[0009] Preferably, the specific steps for assessing the scale and distribution of battery swapping demand in each region within a preset time period based on the predicted battery swapping demand are as follows: Set a threshold for the scale of battery swapping demand, compare the predicted value of battery swapping demand in each region with the threshold, and divide the region into high-demand regions and low-demand regions. High-demand areas are marked as key areas of concern, and the priority of battery reserve allocation for battery swapping stations in these areas is increased. Medium-demand areas are allocated resources according to normal demand, and unnecessary battery replenishment is reduced in low-demand areas, with surplus batteries allocated to high-demand areas. By combining the spatial distribution data of the predicted battery swapping demand, a heat map of regional battery swapping demand is drawn to identify the concentration points of battery swapping demand in each sub-region.

[0010] Preferably, the specific steps for obtaining the battery health prediction value are as follows: Extract voltage time-series data, temperature data, and battery rated parameters from the preprocessed battery swapping cabinet dataset; Analyze the correlation between voltage fluctuations, temperature changes, and current battery performance, and establish a battery performance evaluation model; Based on the model, a quantitative analysis of the current performance state of the battery is performed to obtain a predicted value for battery health.

[0011] Preferably, the specific steps for selecting healthy batteries that meet user needs are as follows: Extract users’ vehicle model and battery type range requirements from the preprocessed user dataset to determine users’ battery health and full-charge range requirements. The battery health prediction value is compared with the user's battery requirements to select batteries whose health and full-charge range meet the user's needs. The filtered batteries are sorted from highest to lowest health status, and the healthiest batteries in the highest ranking are matched with the user first.

[0012] Preferably, the specific steps for obtaining the predicted load value of the regional battery swapping cabinet are as follows: Extract the real-time load battery reserve data of the battery swapping cabinet from the preprocessed battery swapping cabinet dataset, and combine it with the predicted battery swapping demand to obtain the changing trend of battery swapping demand in the region. The study analyzes the changing pattern of real-time load of battery swapping cabinets with battery swapping demand, sets a congestion correction coefficient based on the number of real-time available slots, and analyzes the proportion of available slots and congestion warning time of each battery swapping cabinet in the future preset time period based on the coefficient. The congestion correction factor is used to correct the proportion of idle storage space and the congestion warning time. Then, the corrected proportion of idle storage space and the congestion warning time are integrated to obtain the predicted load value of the regional battery swapping cabinet.

[0013] Preferably, the specific steps for obtaining the distance assessment value are as follows: Extract real-time user location coordinates from the preprocessed user dataset, and extract the geographic coordinates of each battery swapping cabinet from the preprocessed battery swapping cabinet dataset. Obtain the actual travel distance between the user's real-time location coordinates and the geographical coordinates of each battery swapping station, and at the same time, combine real-time traffic data to correct the travel time corresponding to the distance; The actual travel distance and travel time are quantified and converted to obtain a distance assessment value that represents the convenience of users to reach each battery swapping station.

[0014] Preferably, the specific steps for obtaining the recommended evaluation value of the battery swapping cabinet are as follows: A correlation analysis was performed on the preprocessed user dataset, battery swapping cabinet dataset, and environmental dataset to obtain the scenario adaptation factors corresponding to each dimension of the data. By combining the scenario adaptation factor as a weighting coefficient with the predicted value of battery swapping demand, the predicted value of battery health, the predicted value of regional battery swapping cabinet load, and the distance assessment value, a comprehensive analysis is conducted to obtain the recommended assessment value of each battery swapping cabinet.

[0015] A method for positioning reminders and planning of multi-area battery swapping cabinets includes the following steps: Step 1: Collect user datasets, battery swapping cabinet datasets, and environmental datasets within the target service area, and preprocess the user datasets, battery swapping cabinet datasets, and environmental datasets. Step 2: Conduct a comprehensive analysis of the preprocessed user dataset and environmental dataset to obtain the predicted value of battery swapping demand, and evaluate the scale and distribution of battery swapping demand in each region within the future preset time period based on the predicted value of battery swapping demand. Step 3: Perform a comprehensive analysis on the preprocessed battery swapping cabinet dataset to obtain battery health prediction values. Based on the battery health prediction values, evaluate the current performance status of each battery in the battery swapping cabinet and select healthy batteries that meet the user's needs. Step 4: Perform a comprehensive analysis on the preprocessed battery swapping cabinet dataset and the predicted battery swapping demand to obtain the predicted load value of the regional battery swapping cabinets, and assess the idle status and congestion risk of each battery swapping cabinet in the future preset time period based on the predicted load value of the regional battery swapping cabinets. Step 5: Perform a comprehensive analysis on the user location data in the preprocessed user dataset and the battery swapping cabinet location data in the preprocessed battery swapping cabinet dataset to obtain the distance evaluation value, and evaluate the convenience of users to reach each battery swapping cabinet based on the distance evaluation value. Step 6: Perform correlation analysis on the preprocessed user dataset, battery swapping cabinet dataset, and environmental dataset to obtain the scenario adaptation factor. Then, conduct a comprehensive analysis of the scenario adaptation factor with the predicted values ​​of battery swapping demand, battery health, regional battery swapping cabinet load, and distance assessment to obtain the recommended evaluation value of the battery swapping cabinet. Based on the recommended evaluation value, select the optimal battery swapping cabinet and the alternative battery swapping cabinet from the battery swapping cabinets in each region.

[0016] Beneficial effects The present invention has the following beneficial effects: (1) The multi-region battery swapping cabinet positioning reminder and planning system and method, through the set battery swapping demand prediction module, not only enables users to accurately match the battery swapping cabinet with sufficient supply and demand when swapping batteries, avoiding battery swapping failure caused by battery shortage, but also provides data support for battery reserve planning and regional layout optimization of the battery swapping cabinet, avoiding the waste of service interruption in high demand areas and resource backlog in low demand areas.

[0017] (2) The multi-area battery swapping cabinet location reminder and planning system and method, by setting up a comprehensive recommendation module, not only allows users to quickly find reliable and convenient battery swapping cabinets, reducing detours and waiting time, but also provides a basis for the resource allocation and priority scheduling of battery swapping cabinets, avoiding the problem of unbalanced utilization of battery swapping cabinets due to uneven resource allocation.

[0018] (3) The multi-area battery swapping cabinet positioning reminder and planning system and method, by setting up a load prediction module and a congestion warning mechanism, not only informs users of the congestion status of the battery swapping cabinet in advance and recommends alternative solutions to avoid users being unable to swap batteries in time after arriving at the store, but also provides a reference for the operation and maintenance of the battery swapping cabinet and temporary expansion planning, thus avoiding the service shortcomings of the battery swapping cabinet operating under overload for a long time or not being replenished in time.

[0019] (4) The multi-regional battery swapping cabinet positioning reminder and planning system and method, by setting up scene adaptation factor verification and regional battery swapping demand heat map analysis functions, not only frees users from the trouble of wasted trips due to incompatible vehicle models and regional traffic restrictions, but also provides accurate directions for the new site selection and redundant migration of battery swapping cabinets, avoiding the problems of high operating costs and insufficient user coverage caused by blind layout of battery swapping cabinets.

[0020] (5) The multi-region battery swapping cabinet positioning reminder and planning system and method, by setting up a cross-regional battery dynamic allocation and battery swapping cabinet endurance matching mechanism, not only ensures that users can obtain sufficient endurance after swapping batteries and avoid the trouble of insufficient endurance, but also realizes the efficient circulation of surplus batteries between battery swapping cabinets, avoiding the resource mismatch problem of some battery swapping cabinets having idle batteries and some battery swapping cabinets having a shortage of batteries.

[0021] (6) The multi-area battery swapping cabinet positioning reminder and planning system and method, by setting up real-time status monitoring and abnormal early warning functions for the battery swapping cabinet, not only allows users to obtain the availability status of the battery swapping cabinet in real time, avoiding the problem of encountering faults or no batteries when going there, but also provides accurate positioning for the inspection, maintenance and fault handling planning of the battery swapping cabinet, avoiding the risk of service interruption due to untimely maintenance of the battery swapping cabinet.

[0022] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0023] Figure 1 This is a structural diagram of a multi-area battery swapping cabinet positioning reminder and planning system according to the present invention; Figure 2 This is a flowchart of a multi-area battery swapping cabinet positioning reminder and planning method according to the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] This invention provides a technical solution: a multi-area battery swapping cabinet location reminder and planning system, comprising: The data acquisition module is used to collect user datasets, battery swapping cabinet datasets, and environmental datasets within the target service area, and to preprocess these datasets. Specifically, the user dataset includes user location data and user feature data. User location data includes real-time user location coordinates and historical battery swapping location coordinates. User feature data includes user vehicle parameters, compatible battery model, current remaining battery power, and range requirements. Real-time user location coordinates are collected via a satellite positioning module built into the user's mobile terminal or an in-vehicle positioning device after user authorization. The positioning module establishes a communication connection with the GPS or BeiDou satellite navigation system, updating every 30 seconds when in motion and every 5 minutes when stationary to ensure timeliness. Historical battery swapping location coordinates do not require additional active collection; the system automatically associates the user's location coordinates with the current location after each battery swap and stores them in the backend database, allowing for direct extraction from historical battery swapping records later. The actual travel distance is obtained from the cycling path length returned by navigation software. This distance is determined by comparing the straight-line distance with the actual travel distance on 100 different road segments within the target service area, accurately reflecting the common deviations of non-straight-line driving in urban roads. User vehicle parameters are manually entered by the user during system registration or automatically extracted by scanning the vehicle identification code on the mobile terminal to connect to a compliant vehicle information interface. The core features include… Key information such as battery compartment dimensions, interface type, motor rated power, and vehicle curb weight is included. The compatible battery model is automatically generated based on collected user vehicle model parameters and a built-in vehicle and battery model compatibility table; users can manually correct or supplement this information. The current remaining battery charge is collected in real-time through a compliant data communication link established between the vehicle's battery management system and the system, including remaining capacity and percentage. The battery management system monitors the battery status in real-time and uploads this information synchronously, updating it every minute. Range requirements are obtained in two ways: manually entered by the user in the system, and based on collected data. The system automatically calculates the current remaining battery capacity and the vehicle's power consumption per 100 kilometers based on the collected data. This calculation is finalized after user confirmation. The power consumption per 100 kilometers is calculated by multiplying the motor's rated power by 0.01 and the vehicle's curb weight by 0.001. This coefficient is derived from the electric vehicle's power consumption model, ensuring that the calculation result is in kilowatt-hours per 100 kilometers, the motor's rated power is in kilowatts, and the vehicle's curb weight is in kilograms. This calculation formula is derived based on the core influencing factors of electric vehicle power consumption and has been verified through numerous actual power consumption tests on different vehicle models. The error between the calculated result and the measured power consumption per 100 kilometers does not exceed 5%.

[0026] The battery swapping cabinet dataset includes location data, battery status data, and operation data. Location data includes the geographical coordinates and area information of each cabinet. This location data is uploaded to the system in real time, allowing operators to view the geographical coordinates, online status, and surrounding demand distribution of all cabinets through a backend visualization interface, which is used for cabinet layout optimization. Battery status data includes voltage time-series data, temperature data, battery health, battery rated parameters, and battery charge / discharge cycle count. Operation data includes battery reserves and the number of available battery slots in real time. The geographical coordinates of each cabinet are obtained via handheld devices during the installation and commissioning phase. Location data is collected on-site by the device and bound to the unique identifier of the battery swapping cabinet after collection. This data is then permanently entered into the system. The geographical location information is automatically generated based on the battery swapping cabinet's geographic coordinates and a publicly available administrative division data interface, clearly identifying the city and district corresponding to the cabinet. Voltage time-series data is collected in real-time by voltage sensors connected to the positive and negative terminals of the battery. The sensors record the battery voltage value every 30 seconds, continuously collecting data to form a complete voltage time-series data stream, which is then uploaded to the system in real-time. Temperature data is collected by a temperature sensor built into the battery compartment of the battery swapping cabinet. The sensor is installed close to the inner wall of the battery compartment and only monitors the surface temperature of the battery, with a collection frequency of once per minute. Battery health is generated by the system through comprehensive analysis of collected voltage time-series data, temperature data, and battery rated parameters. Specifically, it calculates voltage fluctuation rate using voltage time-series data and adjusts the evaluation results based on a temperature correction coefficient. No separate data collection is required. The temperature correction coefficient is set according to the influence of battery operating temperature on performance stability: 1.0 for temperatures ≤35℃, representing the battery's optimal operating state with no performance degradation; 0.9 for temperatures ≤45℃, indicating slight performance degradation requiring a moderate downward adjustment of the health assessment value; and 0.7 for temperatures >45℃. Batteries are subject to overheating risk and significant performance degradation. The coefficient setting is determined based on the battery manufacturer's technical manual and 1000 sets of high-temperature test data. The battery's rated parameters, including rated voltage, rated capacity, and full-charge range, are fixed parameters marked at the factory and manually entered into the system and bound to the battery's unique code when the battery is put into storage. The number of battery charge-discharge cycles is automatically counted and recorded by the battery management module built into the battery swapping cabinet. The data is updated after each battery completes a charge-discharge cycle and uploaded to the system backend at regular intervals. The battery reserve is collected by independent infrared sensors equipped in each compartment of the battery swapping cabinet. The sensors detect that there is a fully charged battery in the compartment with a health level of not less than 0.The battery life counter is 1 for model 6. The full charge determination criterion is that the remaining battery capacity is ≥ 95% of the rated capacity. This standard is set with reference to the charging and discharging characteristics of lithium batteries. In normal charging mode, a lithium battery is close to full charge when it reaches 95% of its rated capacity. The remaining 5% is a safety redundancy, which avoids damage to the battery from overcharging and ensures that users can obtain near-full charge range. This determination criterion is consistent with the full charge protection logic of the battery management system and complies with industry-standard specifications. The real-time number of available battery compartments is calculated based on the total number of compartments in the battery swapping cabinet and the number of occupied compartments. The total number of compartments is a fixed configuration parameter at the factory, with common specifications including 10 compartments and 20 compartments. This number is entered into the system during the installation and commissioning phase and bound to the unique identification number of the battery swapping cabinet. The number of occupied compartments is determined by infrared sensors in each compartment, and the system calculates and updates it in real time.

[0027] The environmental dataset includes traffic data, including a real-time congestion index. The real-time congestion index is obtained through public data interfaces of mainstream navigation software such as Gaode Maps or Baidu Maps. The interfaces push real-time congestion quantification values ​​for each area at a fixed frequency, which are directly synchronized to the system for subsequent analysis. Road travel time is calculated based on the actual travel distance from the user's current location to the battery swapping station and the real-time congestion index. The final result is obtained by dividing the actual travel distance by the average speed of urban roads and then multiplying it by a correction factor of (1 + real-time congestion index). The average speed of urban roads is preset to 25 km / h. This value is determined with reference to the normal driving speed of urban electric vehicles, traffic light waiting, and pedestrian avoidance. If there are special traffic conditions in the target service area, the speed can be manually adjusted to 20 km / h or 30 km / h through the system backend to adapt to the traffic characteristics of different areas.

[0028] Specifically, the preprocessing steps for the collected user dataset, battery swapping cabinet dataset, and environmental dataset are as follows: All parameters of different dimensions that need to participate in subsequent comprehensive analysis are uniformly normalized and converted into dimensionless values ​​in the range of 0 to 1; anomaly removal and signal optimization are performed on the core parameters of each dataset, and classification parameters are uniformly converted into standardized labels; abnormal data exceeding the normal scenario are removed based on the preset effective value range; and the spatiotemporal correspondence between datasets is established through association mapping to complete the preprocessing.

[0029] Furthermore, the normalization process uses the extreme values ​​of each parameter's actual application scenario as the benchmark value, calculates the ratio of each parameter to the benchmark value, eliminates the impact of differences in dimensions, and makes parameters of different dimensions comparable, laying the foundation for subsequent multi-parameter comprehensive analysis: the actual travel distance of the user dataset is based on the maximum travel distance of 50 kilometers in the target service area, the remaining capacity is based on the corresponding battery rated capacity, and the range requirement is based on the maximum range requirement of users in the area of ​​200 kilometers; the battery charge and discharge cycle count of the battery swapping cabinet dataset is based on the rated cycle count of 800 times, and the other health and real-time load parameters are already dimensionless data and do not require additional conversion; the road travel time of the environmental dataset is based on the maximum travel time of 60 minutes in the area, and the real-time congestion index is already dimensionless data and is directly used.

[0030] Anomaly removal in the user dataset is achieved through threshold judgment. Data with a single location coordinate deviation exceeding 1 kilometer and no supporting movement trajectory is judged as drift data. Values ​​that are obviously unrealistic, such as a battery compartment size of 0 and a remaining battery percentage exceeding 100%, are directly removed. When there is a lack of battery life requirements, the data is automatically filled by the correlation between the current remaining battery power and the power consumption standard per 100 kilometers. For signal optimization, a moving average filtering method with a window size of 5 is used for the location data. The arithmetic mean is calculated by taking the current data and the two adjacent data points before and after it to suppress location fluctuations and retain the true movement trend. Standardized labeling converts categorized data such as interface type into a unified Chinese expression, and coordinates are uniformly converted to decimal latitude and longitude format in the WGS84 coordinate system. Numerical data retains the corresponding number of decimal places according to type.

[0031] Anomaly removal in the battery swapping cabinet dataset is based on the 3σ principle. Voltage time-series data and temperature data exceeding the mean ± 3 times the standard deviation are judged as sensor fault data. Data with logical contradictions, such as battery reserves exceeding the total number of bays or the number of idle bays being negative, are directly removed. When there are no more than 5 missing voltage time-series data sets, they are filled by linear interpolation of adjacent data. For signal optimization, a moving average filter with a window size of 5 is used for voltage time-series data to suppress high-frequency fluctuations and retain the true trend of voltage changes. Standardized identification organizes the battery swapping cabinet number into a regional abbreviation-serial number format, the battery code into a battery swapping cabinet number-bay serial number format, and the battery model adopts a unified voltage-capacity standard expression. The coordinates are consistent with the WGS84 coordinate system format of the user dataset.

[0032] Anomaly removal in the environmental dataset is determined by the valid value range. Data with a real-time congestion index exceeding the 0-1 range is considered invalid. Missing data is filled with the average value of the same region during the same period. Data with a congestion index of 0 but a travel time far exceeding the theoretical smooth travel time is corrected according to the theoretical time. Standardized labels organize the road's region according to the city-district format, and the time data is consistent with the user dataset and the battery swapping cabinet dataset. For signal optimization, a moving average filtering method with a window size of 3 is used for road travel time. The arithmetic mean is calculated by taking the current data and one adjacent data point before and after it to suppress the time deviation caused by instantaneous traffic fluctuations.

[0033] The association mapping of all datasets is established through the spatiotemporal dimension. The user dataset and the battery swapping cabinet dataset form a user-battery swapping cabinet correspondence based on coordinate association, and form a user-region correspondence based on association with administrative division data. The battery swapping cabinet dataset forms a three-level mapping relationship of battery swapping cabinet-slot-battery through association with battery code and battery swapping cabinet number, and forms a battery swapping cabinet-region correspondence based on association with administrative division data. The environmental dataset forms a region-traffic status correspondence based on association with administrative division data, and forms a battery swapping cabinet-traffic data correspondence based on association with battery swapping cabinet coordinates.

[0034] All preprocessed data is uniformly tagged with UTC timestamps and automatically converted to Beijing time YYYY-MM-DD HH:MM:SS format when displayed to users or used for local analysis. It is uniformly stored in JSON format, with field names using underscore naming conventions. Data is transmitted to subsequent modules via a data interface, with transmission latency controlled within 100 milliseconds to ensure consistency in the time base of historical and real-time data in subsequent analyses. A timed update mechanism is established: user datasets are updated every 30 seconds, battery swapping cabinet datasets every minute, and environmental datasets every 5 minutes. Preprocessed data undergoes sampling verification with a sampling ratio of no less than 10%, ensuring data validity of no less than 99%, format consistency of 100%, and correlation accuracy of no less than 99.5%.

[0035] If a user's location drifts, the system will automatically detect and prompt the user that the location signal is weak, asking them to check the equipment or refresh the location. At the same time, based on historical battery swapping locations and the current approximate area, the system will provide temporary recommendations, which will be updated after the location is restored. If the voltage, temperature, and other data of the battery swapping cabinet frequently show abnormalities, the system will trigger an equipment fault warning and push it to the operations backend, marking the location of the faulty battery swapping cabinet and the data type of the abnormality. Staff will complete the repair within 24 hours to ensure accurate data collection. For batteries or battery swapping cabinets that cannot calculate health, load, and other indicators due to abnormal data, the system will temporarily mark them as unusable, and will re-evaluate them after the data returns to normal.

[0036] The battery swapping demand forecasting module is used to comprehensively analyze the preprocessed user dataset and environmental dataset to obtain the battery swapping demand forecast value, and to evaluate the scale and distribution of battery swapping demand in each region within a preset time period based on the battery swapping demand forecast value. The battery health assessment module is used to comprehensively analyze the preprocessed battery swapping cabinet dataset, obtain battery health prediction values, and evaluate the current performance status of each battery in the battery swapping cabinet based on the battery health prediction values, and select healthy batteries that meet user needs. The load prediction module is used to comprehensively analyze the preprocessed battery swapping cabinet dataset and the predicted battery swapping demand to obtain the regional battery swapping cabinet load prediction value, and to evaluate the idle status and congestion risk of each battery swapping cabinet in the future preset time period based on the regional battery swapping cabinet load prediction value. The distance assessment module is used to comprehensively analyze the user location data in the preprocessed user dataset and the battery swapping cabinet location data in the preprocessed battery swapping cabinet dataset to obtain the distance assessment value, and to assess the convenience of users to reach each battery swapping cabinet based on the distance assessment value. The comprehensive recommendation module is used to perform correlation analysis on the preprocessed user dataset, battery swapping cabinet dataset, and environmental dataset to obtain scenario adaptation factors. It then performs comprehensive analysis on the scenario adaptation factors, battery swapping demand prediction values, battery health prediction values, regional battery swapping cabinet load prediction values, and distance assessment values ​​to obtain battery swapping cabinet recommendation assessment values. Based on the battery swapping cabinet recommendation assessment values, it selects the optimal battery swapping cabinet and alternative battery swapping cabinets from the battery swapping cabinets in each region.

[0037] Specifically, the steps to obtain the battery swapping demand forecast are as follows: Extract all battery swap records of the target user within the past 3 months, count the number of battery swaps for the user in the same time period according to the preset time period and calculate the average value to obtain the historical battery swap frequency of a single user; extract all battery swap records of all users in the same area and the same preset time period within the past 3 months, count the total number of battery swaps in that time period and calculate the average value to obtain the historical battery swap frequency of the same period in the area. The extracted single-user battery swapping data and regional battery swapping data are grouped by time dimension according to preset time periods and by spatial dimension according to the region to which the battery swapping cabinet belongs, thus completing the correlation and matching of time and spatial dimensions. The average real-time occupancy rate of all battery swapping cabinets in the region is obtained, and a occupancy adjustment coefficient is set based on this average. When the occupancy rate is ≥80%, a corresponding adjustment coefficient is set; when the occupancy rate is 50%≤ and <80%, a corresponding adjustment coefficient is set; when the occupancy rate is <50%, a corresponding adjustment coefficient is set. The correlated and matched user data, regional data and occupancy adjustment coefficient are combined to form a regional battery swapping demand analysis sample. Based on the regional battery swapping demand analysis sample, the average of the historical battery swapping frequency of a single user and the historical battery swapping frequency of the same period in the region is taken, and then the result is correlated with the warehouse occupancy adjustment coefficient to obtain the predicted value of battery swapping demand in each region in the future preset period.

[0038] The specific method for obtaining the battery swapping demand forecast is as follows: In the formula, This represents the projected demand for battery swapping, specifically the total number of battery swaps expected in a certain region within a preset future time period, reflecting the scale of battery swapping demand in that region. This represents the historical battery swapping frequency of a single user, specifically the average number of battery swaps for a user within the same preset time period (e.g., 1 hour, 3 hours) over the past 3 months. It is obtained by extracting the user's battery swapping records over the past 3 months and statistically analyzing them by time period, reflecting the battery swapping behavior pattern of a single user. This indicates the historical frequency of battery swapping in the same region during the same period. Specifically, it is the average total number of battery swaps in the same region and the same preset time period within the past 3 months. It is obtained by extracting all battery swapping records for the same period in the region and reflecting the overall trend of battery swapping demand in the region. This indicates the bay occupancy adjustment coefficient, specifically a correction coefficient set based on the real-time bay occupancy rate of the battery swapping cabinet: when the bay occupancy rate is ≥80%. =1.2 (reflects tight battery supply in the region, with actual demand exceeding the baseline data), when 50% ≤ warehouse occupancy rate < 80%. =1.0 (reflecting a basic balance between supply and demand), when the position occupancy rate is <50%. =0.8 (reflecting sufficient battery supply and relatively low actual demand). This coefficient is based on the historical operating data of operators over the past 6 months and is used to reflect the true supply and demand relationship.

[0039] Specifically, the steps for assessing the scale and distribution of battery swapping demand in each region within a predetermined time period based on the predicted battery swapping demand are as follows: A threshold for battery swapping demand is set. This threshold is determined based on the historical average and maximum peak value of battery swapping demand in the target service area over the past six months. The high demand threshold is set at 1.5 times the historical average. According to statistics, when the demand exceeds 1.5 times the historical average, the available battery swapping slots are less than 30%, and the allocation priority needs to be increased. The medium demand threshold is set between 0.8 and 1.5 times the historical average. In this range, the supply and demand of battery swapping slots are basically balanced. The low demand threshold is set at 0.8 times the historical average. In this range, the battery supply of battery swapping slots is sufficient and there is no need for frequent replenishment. High-demand areas are marked as key areas of concern, and the battery reserve allocation priority of the battery swapping cabinets in these areas is set to Level 1, with batteries replenished every 2 hours to ensure that the full-charge battery coverage of the idle slots is not less than 90%. For medium-demand areas, resources are allocated according to normal demand, with allocation priority set to Level 2, and batteries are replenished every 4 hours to maintain a full-charge battery coverage of not less than 70%. For low-demand areas, unnecessary battery replenishment is reduced, allocation priority is set to Level 3, and replenishment is only required once every 8 hours. Surplus full-charge batteries are uniformly allocated to high-demand areas through the regional dispatch center to achieve dynamic balance of battery resources. Based on users' battery life needs, the core requirements for batteries are defined. The battery health level must be no less than 0.6. This threshold is determined based on the battery manufacturer's technical manual and feedback from 500 groups of users. When the health level is ≥0.6, the battery life degradation is ≤20%, which can guarantee the user's basic usage needs. The full charge range must be no less than the user's battery life needs to ensure that the usage range meets the standard. At the same time, the remaining capacity must be ≥95% of the rated capacity. This requirement is consistent with the full charge judgment standard of battery reserve, forming a battery selection standard exclusive to users. For high-demand areas, if battery swapping demand continues to exceed the historical average by 1.5 times after replenishing batteries at the first-level allocation frequency, and the idle capacity of battery swapping cabinets is less than 20%, the system will automatically trigger cross-regional emergency allocation, dispatching surplus fully charged batteries from surrounding low-to-medium demand areas to prioritize replenishing the core battery swapping cabinets in that area. At the same time, the operations team will be notified to arrange expedited replenishment, shortening the replenishment interval to 1 hour. For low-demand areas, if battery backlog continues for more than 24 hours and the idle capacity is ≥70%, the system will automatically generate a battery transfer instruction and push it to the operations backend, reminding staff to transfer surplus batteries to adjacent medium-demand areas to avoid long-term idleness. For medium-demand areas, if demand suddenly surges to the high-demand threshold, the system will automatically and temporarily upgrade the allocation priority to first-level, and then restore it to second-level after 2 hours to ensure supply and demand balance.

[0040] For batteries stockpiled in low-demand areas, the system automatically records the idle time. Batteries idle for more than 7 days trigger a regular maintenance instruction, and operators perform charge and discharge maintenance during inspections to replenish the battery to 80% capacity to prevent battery depletion. If the number of stockpiled batteries exceeds 50% of the total battery swapping station capacity in the area and remains idle for more than 12 hours, the system automatically generates a cross-regional transfer suggestion and pushes it to the operations backend, prioritizing transfer to adjacent high- or medium-demand areas to ensure efficient utilization of battery resources.

[0041] Based on the division of high, medium, and low demand areas, the system generates a battery swapping station location planning report: for high demand areas, it is recommended to add new battery swapping stations, for example, a spacing of ≤1 km is suggested; for medium demand areas, the existing battery swapping station density is maintained, for example, a spacing of ≤2 km is suggested; for low demand areas, it is recommended to relocate redundant battery swapping stations to adjacent medium- and high demand areas to reduce operating costs.

[0042] Specifically, the steps to obtain the battery health prediction value are as follows: From the preprocessed battery swapping cabinet dataset, extract the voltage time series data of a single battery for the past hour. This voltage time series data consists of continuous voltage records collected every 30 seconds. Also extract the temperature data for the past hour, which consists of battery surface temperature records collected every minute. Finally, extract the battery's rated parameters, which include the rated voltage and the maximum design charge-discharge cycle count marked at the factory. Also extract the cumulative charge-discharge cycle count of the battery from the factory to the present through the battery management module built into the battery swapping cabinet. Based on 1000 sets of battery performance test data under different operating conditions, covering battery performance degradation samples with different voltage fluctuation ranges, temperature ranges, and cycle counts, a battery performance evaluation model was established using a linear regression algorithm. The model input parameters are voltage fluctuation rate, temperature correction coefficient, and cycle loss ratio, and the output is the quantitative result of battery performance. The model fit R is [value missing]. 2 ≥0.85, ensuring the accuracy of the evaluation results. The core logic of this model is that the voltage fluctuation rate reflects the battery stability, the temperature correction coefficient reflects the battery working state, and the cycle loss ratio reflects the remaining battery life. The three are directly multiplied to achieve performance quantification. The battery performance evaluation model is used to quantitatively analyze the current performance status of the battery. First, the difference between the maximum and minimum voltage values ​​is calculated using voltage time-series data. Then, this difference is divided by the battery's rated voltage to obtain the voltage fluctuation rate, which reflects the battery's voltage stability. Based on the real-time collected battery temperature, a corresponding temperature correction coefficient is determined: 1.0 for temperatures ≤35℃, 0.9 for temperatures ≤45℃, and 0.7 for temperatures >45℃. The cycle loss ratio is obtained by comparing the cumulative number of charge-discharge cycles with the factory-specified maximum number of charge-discharge cycles. The voltage fluctuation rate is then multiplied by its inverse value (1 - voltage fluctuation rate), and the cycle loss ratio is multiplied by its inverse value (1 - cycle loss ratio). Finally, these values ​​are multiplied continuously with the temperature correction coefficient to obtain the predicted battery health value.

[0043] The specific method for obtaining battery health prediction values ​​is as follows: In the formula, This represents the battery health prediction value, specifically the current performance quantification value of a single battery in the battery swapping cabinet (range 0-1, the larger the value, the healthier the battery), used to screen reliable batteries suitable for users; This represents the voltage fluctuation rate, specifically the degree of fluctuation in the battery's voltage time-series data over the past hour. It is calculated by subtracting the minimum voltage from the maximum voltage and then dividing by the battery's rated voltage, reflecting the battery's voltage stability. This indicates the temperature correction factor, specifically the performance correction factor set according to the battery operating temperature: when the temperature is ≤35℃ =1.0 indicates that the battery is in its optimal operating condition when 35℃ < temperature ≤ 45℃. =0.9 indicates a slight degradation in battery performance. When the temperature is >45℃, t=0.7 indicates that the battery is at risk of overheating and its performance is significantly degraded. This coefficient is determined based on the battery manufacturer's technical manual and 1000 sets of high-temperature test data. This indicates the actual number of charge-discharge cycles of the battery, specifically the cumulative number of charge-discharge cycles from the time the battery left the factory until now, which is automatically calculated by the battery management module built into the battery swapping cabinet. This indicates the rated number of battery cycles, specifically the maximum design charge-discharge cycle count indicated when the battery leaves the factory. For example, the industry standard is 800 cycles, which is the benchmark value for measuring battery cycle life.

[0044] Specifically, the steps for selecting healthy batteries that meet user needs are as follows: From the preprocessed user dataset, the vehicle model parameters of the user are extracted, including the battery compartment size and interface type, and range requirement data. Based on the vehicle model parameters and the vehicle battery compatibility table built into the system, the corresponding compatible battery model for the user is determined.

[0045] From the preprocessed battery swapping cabinet dataset, the health prediction values, full-charge range parameters, and rated parameters of all batteries in each cabinet are extracted, clearly indicating the battery model. The battery models are then initially matched with the user-compatible battery models to filter out compatible batteries. Next, the health prediction values ​​of the compatible batteries are compared with the user's set health requirements, and the full-charge range parameters are compared with the user's range requirements. Batteries with a health level of not less than 0.6 and a full-charge range not less than the user's range requirements are retained, completing the second filtering.

[0046] For qualified batteries after secondary screening, they are sorted from high to low according to their health prediction values. If there are batteries with the same health prediction value during the sorting process, they are sorted from high to low according to their full-charge range. Finally, the healthiest batteries in the highest ranking are matched to users to ensure that users get batteries with better performance and higher reliability. For batteries with a health score below 0.6 after secondary screening, the system automatically marks them as pending and isolates them in a dedicated testing compartment using the built-in compartment locking function of the battery swapping cabinet, prohibiting their use by users. Simultaneously, a battery anomaly warning is generated and pushed to the operator's backend management system, clearly indicating the battery code, predicted health value, and location of the swapping cabinet, reminding staff to conduct specialized testing. Upon receiving the warning, staff disassemble and inspect the substandard batteries, checking for abnormal voltage fluctuations, excessive temperature, or excessive cycle loss. For repairable batteries, maintenance operations such as equalization charging and replacement of faulty components are performed. After maintenance, the batteries are reconnected to the system, and the predicted health value is recalculated according to the battery health assessment process. Once the value meets the standard, the isolation is lifted, and the batteries are added to the available battery pool. For irreparable batteries, they are recycled and disposed of according to environmental protection requirements, and the battery reserve data of the swapping cabinet is updated to ensure the accuracy of the available battery count reported by the system. For batteries whose full-charge range does not meet user needs, the system automatically marks them as substandard, isolates them in a dedicated testing compartment, prohibits their recommendation to users, and simultaneously pushes an alert to the operations backend, labeling the battery code and its associated battery swapping cabinet. Upon receiving the alert, staff will conduct charge and discharge tests on the battery. If the insufficient range is due to incomplete charging, it will be fully charged again, and once the battery meets the standards, it will be removed from the isolation list and added to the available battery pool. If the insufficient range is due to battery degradation and the battery health is below 0.6, it will be handled according to the non-compliant battery recycling and disposal process. If the battery health is ≥0.6, but the range is still substandard, the battery's target user group will be adjusted, and it will be recommended to users with lower range requirements.

[0047] Specifically, the steps to obtain the predicted load value of the regional battery swapping cabinet are as follows: From the preprocessed battery swapping cabinet dataset, the total number of battery swapping slots and the number of slots currently occupied are extracted for each cabinet. The current occupancy rate of each battery swapping cabinet is calculated by the ratio of the number of occupied slots to the total number of slots. At the same time, the previously obtained regional battery swapping demand forecast is retrieved, and combined with the daily and time-period variation patterns of the regional battery swapping demand over the past month, the trend of the regional battery swapping demand in the future preset time period is analyzed. Possible trends include rising demand, stable demand, and declining demand.

[0048] Based on the changing trends in battery swapping demand, the correlation between battery swapping cabinet load and demand is analyzed. When demand increases, the occupancy rate of the swapping cabinets is likely to continue to increase, and the congestion risk increases accordingly. When demand is stable, the occupancy rate remains within the current range, and the congestion risk is stable. When demand decreases, the occupancy rate gradually decreases, and the congestion risk is alleviated. A congestion correction coefficient is set based on the real-time number of idle swapping cabinets. The number of idle cabinets is the total number of cabinets minus the number of occupied cabinets. When the number of idle cabinets is greater than or equal to 50% of the total number of cabinets, the coefficient is set to 0.1, indicating that the swapping cabinet is idle and there is almost no congestion. When the number of idle cabinets is less than or equal to 30% and less than 50%, the coefficient is set to 0.5, indicating that the swapping cabinet is in a semi-saturated state and there is a slight risk of congestion. When the number of idle cabinets is less than 30%, the coefficient is set to 0.9, indicating that the swapping cabinet is close to saturation and the risk of congestion is high. Combining the above patterns and coefficients, the changing trend of the proportion of idle cabinets in each swapping cabinet and the congestion warning time are analyzed within a preset period. A congestion warning is triggered when the predicted load value is greater than or equal to 0.8.

[0049] Based on the current occupancy rate as the base data, and combined with the set congestion correction coefficient, a weighted summation method is used to correct the previously analyzed idle warehouse ratio and congestion warning time (current warehouse occupancy rate weight 0.6, congestion correction coefficient weight 0.4) to ensure that the data reflects future demand trends. Then, the corrected warehouse occupancy rate and the congestion correction coefficient are added together and the arithmetic mean is taken to obtain the regional battery swapping cabinet load prediction value. This value ranges from 0 to 1. The larger the value, the higher the battery swapping cabinet load and the stronger the congestion risk, which is used to accurately assess the service pressure of the battery swapping cabinet.

[0050] The specific method for obtaining the predicted load value of the regional battery swapping cabinet is as follows: In the formula, This represents the predicted load value of the battery swapping cabinets in the area. Specifically, it is the quantitative value of the load and congestion risk of a certain battery swapping cabinet. The specific value ranges from 0 to 1. The larger the value, the higher the load and the stronger the congestion risk. It is used to assess the service pressure of the battery swapping cabinets. This indicates the occupancy rate of the battery swapping station, specifically the ratio of the number of occupied stations to the total number of stations. It is calculated using data from the infrared sensors in each station of the battery swapping station and directly reflects the current battery storage saturation level of the station. The congestion correction coefficient is a potential congestion correction value set based on the real-time number of available slots in the battery swapping station: when the number of available slots is greater than or equal to 50% of the total slots, y=0.1, indicating that the battery swapping station is idle and there is almost no congestion; when the number of available slots is less than or equal to 30% and the number of available slots is less than 50%, y=0.5, indicating that the battery swapping station is in a semi-saturated state and there is a slight risk of congestion; when the number of available slots is less than 30%, y=0.9, indicating that the battery swapping station is close to saturation and there is a high risk of congestion. This coefficient is derived from statistics based on the actual usage scenarios of the battery swapping station. When the predicted load of a battery swapping station in a given area is ≥0.8, triggering a congestion warning, the system immediately sends a congestion alert to users within a 3-kilometer radius of the station. Simultaneously, it recommends alternative battery swapping stations with lower current loads and provides real-time routes. For users already at the station, the system sends the estimated waiting time. The operations team receives the warning information concurrently. If the congestion lasts for more than 30 minutes, staff are dispatched to the site to assist with battery swapping and manage the flow of people. For battery swapping stations that trigger congestion warnings three times consecutively, the system automatically suggests increasing the battery reserve of the station or adding more battery swapping stations in the surrounding area to alleviate long-term congestion.

[0051] If a user goes to the recommended battery swapping station and finds no available slots or batteries, the system automatically detects battery swapping stations within a 3-kilometer radius with a load below 0.5, recommends the best alternative, provides real-time navigation, and offers the user a battery swapping coupon as compensation. The operations team simultaneously receives on-site power shortage alerts from users. If the same battery swapping station experiences three consecutive instances of no available slots, the system automatically increases the allocation priority of that station, shortens the recharge interval, and, if necessary, arranges a temporary mobile recharge vehicle to replenish batteries.

[0052] Specifically, the steps to obtain the distance assessment value are as follows: From the preprocessed user dataset, real-time positioning coordinates are extracted from the user's authorized mobile terminal built-in satellite positioning module or vehicle positioning device. These real-time positioning coordinates are obtained based on GPS or Beidou satellite navigation system to ensure the accuracy of location information. From the preprocessed battery swapping cabinet dataset, the geographic coordinates of each battery swapping cabinet are extracted from the field collected by handheld positioning device during the installation and commissioning phase and bound to the unique identification number. These geographic coordinates and user positioning coordinates use the same WGS84 coordinate system to ensure the consistency of subsequent distance calculations.

[0053] Based on the extracted real-time user location coordinates and the geographical coordinates of each battery swapping station, the system calls the riding mode data of mainstream navigation software to directly obtain the actual travel distance and travel time. The actual travel distance is the length of the electric vehicle riding route returned by the navigation software. This route length already includes actual scenarios such as detours to non-motorized vehicle lanes and turns at intersections, so no additional correction is needed. The travel time is the estimated time for riding the electric vehicle returned by the navigation software. This estimated time has been adapted to scenarios such as non-motorized vehicle traffic congestion and waiting at traffic lights.

[0054] The maximum travel distance and maximum travel time benchmarks for the region are determined. The maximum travel distance benchmark is the maximum measured travel distance from users to battery swapping stations within the target service area, with a fixed value set at 50km. This value is determined based on actual measurements of the geographical scope of the target service area. The maximum travel time benchmark is the maximum measured travel time from users to battery swapping stations within the target service area, with a fixed value set at 60min. This value is determined based on actual measurements of the traffic conditions in the target service area. The actual travel distance is divided by the maximum travel distance benchmark to obtain normalized distance data, and the travel time is divided by the maximum travel time benchmark to obtain normalized time data. The arithmetic mean of the two sets of normalized data is taken to obtain the distance evaluation value characterizing the convenience of users to each battery swapping station. This value ranges from 0 to 1, with a smaller value indicating higher convenience for users to reach the battery swapping station.

[0055] The distance assessment value is obtained as follows: In the formula, This represents the distance assessment value, specifically a quantitative value of how convenient it is for a user to reach a certain battery swapping station. The value ranges from 0 to 1, with a smaller value indicating greater convenience. It is used to comprehensively measure the cost for a user to travel to the battery swapping station. Indicates the actual travel distance; This represents the maximum travel distance benchmark in the area, specifically the maximum measured travel distance from users to the battery swapping station within the target service area. For example, a fixed value of 50km is used to normalize the actual travel distance into a dimensionless value. This indicates the estimated travel time on the road, specifically the estimated time it would take for a user to travel by electric scooter to the battery swapping station. This represents the maximum travel time benchmark for the area, specifically the maximum measured travel time from the user to the battery swapping station within the target service area. For example, a fixed value of 60 minutes is used to normalize the actual travel time into a dimensionless value.

[0056] Specifically, the steps to obtain the recommended evaluation value for the battery swapping cabinet are as follows: The preprocessed user dataset, battery swapping cabinet dataset, and environmental dataset are retrieved, and a multi-dimensional correlation analysis is performed on the three types of data. User vehicle parameters and regional traffic requirements are extracted from the user dataset. The vehicle parameters include battery compartment size and interface type. The battery model, interface type, and regional information of each battery swapping cabinet are extracted from the battery swapping cabinet dataset. The electric vehicle traffic restriction rules for each region are extracted from the environmental dataset. The correlation logic is clarified through data cross-comparison. If the vehicle parameters and battery model and interface type match perfectly, the vehicle adaptation meets the standard. If there are no electric vehicle traffic restrictions in the area where the battery swapping cabinet is located, the regional adaptation meets the standard. The scenario adaptation factor is determined based on the correlation results. If both vehicle adaptation and regional adaptation meet the standard, the factor value is 1. If the vehicle is adapted but there are regional restrictions or the vehicle is not adapted, the value is 0 regardless of whether there are regional restrictions, ensuring that the scenario adaptation factor truly reflects the availability of the battery swapping cabinet.

[0057] If the scenario compatibility factor is 0, the system hides the battery swapping station in the recommendation results and clearly informs the user of the reason for incompatibility, such as vehicle model incompatibility or regional restrictions. If there is no compatible battery swapping station in the current user's area, the system automatically expands the recommendation range to adjacent areas, filters battery swapping stations with a compatibility factor of 1, sorts them by distance evaluation value from smallest to largest, and provides detailed route planning to ensure that the user can find an available battery swapping station.

[0058] Collect the core indicators calculated above, including the battery health prediction value, which reflects battery performance reliability; the regional battery swapping cabinet load prediction value, the inverse value of which is the battery swapping cabinet idle level (the lower the load, the higher the idle level); the distance assessment value, the inverse value of which is the battery swapping convenience (the smaller the assessment value, the higher the convenience); and the battery swapping demand prediction value. Simultaneously, determine the regional maximum battery swapping demand benchmark. If the preset time period is more than 1 hour, the regional maximum battery swapping demand benchmark is scaled according to the preset time period length. For example, if the preset time period is 3 hours, the regional maximum battery swapping demand benchmark = 20 times / hour × 3 = 60 times / 3 hours. Ensure that the battery swapping demand prediction value and the regional maximum battery swapping demand benchmark have consistent units. This benchmark is the historically measured maximum battery swapping demand in the target service area, fixed at 20 times per hour. This value is determined based on the battery swapping peak data of the target service area over the past six months. Divide the battery swapping demand prediction value by the regional maximum battery swapping demand benchmark to complete the normalization processing of the battery swapping demand data, transforming it into a dimensionless value.

[0059] The system integrates scenario adaptation factors, battery health prediction values, battery swapping cabinet idleness (1 − predicted load value of regional battery swapping cabinets), battery swapping convenience (1 − distance assessment value), and normalized battery swapping demand data. The five indicators are summed, and the summation result is divided by 5 to obtain the arithmetic mean. The recommended evaluation value of each battery swapping cabinet is obtained. The value ranges from 0 to 1. The larger the value, the better the overall performance of the battery swapping cabinet in terms of adaptability, battery health, idleness, convenience, and demand matching, and the higher the recommendation priority.

[0060] The specific method for obtaining the recommended evaluation value for the battery swapping cabinet is as follows: In the formula, This represents the recommended evaluation value for a battery swapping cabinet, specifically the comprehensive recommendation priority quantification value of a certain battery swapping cabinet (the value ranges from 0 to 1, with a larger value indicating a higher recommendation priority), which is used to select the optimal option from battery swapping cabinets in multiple regions; The scenario adaptation factor represents the compatibility status between the battery of the battery swapping station and the user's vehicle model. For example, it is set to 1 when compatible and 0 when incompatible. It is obtained by combining regional traffic restrictions. The regional electric vehicle traffic restriction rules are extracted from the administrative division association data of the environmental dataset to ensure that the rule acquisition path is clear. It is set to 1 when there are no restrictions, which reflects the basic compatibility of the battery swapping station with the user. This represents the predicted battery health value, calculated using the same formula as above, reflecting the performance reliability of the batteries within the battery swapping cabinet; 1− This indicates the idle status of the battery swapping cabinet, and is the inverse value of the load forecast. The smaller the value, the larger the value, reflecting the congestion situation of the battery swapping cabinet; 1− This indicates the ease of battery swapping, and is the inverse value of the distance assessment. The smaller the value, the larger the value, reflecting the convenience for users to go to the battery swapping station; This represents the predicted demand for battery swapping, calculated using the same formula as above. This represents the benchmark for the maximum battery swapping demand in the region, specifically the maximum measured battery swapping demand within the target service area, such as 20 swaps / hour. It is used to normalize the predicted battery swapping demand into a dimensionless value, reflecting the demand matching degree of the area where the battery swapping station is located. After selecting the optimal and alternative battery swapping stations, the system monitors the status of the optimal station in real time. If the optimal station suddenly becomes full or malfunctions while the user is en route, the system automatically switches to the top-ranked alternative station and notifies the user via mobile device, while also updating the navigation route. If the user rejects the recommended optimal station, the system displays a simple option for the user to choose the reason for rejection, including distance, congestion, or poor reputation. Relevant data is synchronized to the backend to optimize the parameters of the recommendation model. Alternative stations are ranked from highest to lowest based on their recommendation evaluation value, and are replaced sequentially when the optimal station is unavailable. The ranking is also dynamically adjusted in real time based on the load and battery health of each station.

[0061] A method for positioning reminders and planning of multi-area battery swapping cabinets, such as Figure 2 As shown, it includes the following steps: Step 1: Collect user datasets, battery swapping cabinet datasets, and environmental datasets within the target service area, and preprocess the user datasets, battery swapping cabinet datasets, and environmental datasets. Step 2: Conduct a comprehensive analysis of the preprocessed user dataset and environmental dataset to obtain the predicted value of battery swapping demand, and evaluate the scale and distribution of battery swapping demand in each region within the future preset time period based on the predicted value of battery swapping demand. Step 3: Perform a comprehensive analysis on the preprocessed battery swapping cabinet dataset to obtain battery health prediction values. Based on the battery health prediction values, evaluate the current performance status of each battery in the battery swapping cabinet and select healthy batteries that meet the user's needs. Step 4: Perform a comprehensive analysis on the preprocessed battery swapping cabinet dataset and the predicted battery swapping demand to obtain the predicted load value of the regional battery swapping cabinets, and assess the idle status and congestion risk of each battery swapping cabinet in the future preset time period based on the predicted load value of the regional battery swapping cabinets. Step 5: Perform a comprehensive analysis on the user location data in the preprocessed user dataset and the battery swapping cabinet location data in the preprocessed battery swapping cabinet dataset to obtain the distance evaluation value, and evaluate the convenience of users to reach each battery swapping cabinet based on the distance evaluation value. Step 6: Perform correlation analysis on the preprocessed user dataset, battery swapping cabinet dataset, and environmental dataset to obtain the scenario adaptation factor. Then, conduct a comprehensive analysis of the scenario adaptation factor with the predicted values ​​of battery swapping demand, battery health, regional battery swapping cabinet load, and distance assessment to obtain the recommended evaluation value of the battery swapping cabinet. Based on the recommended evaluation value, select the optimal battery swapping cabinet and the alternative battery swapping cabinet from the battery swapping cabinets in each region.

[0062] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0063] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A multi-area battery swapping cabinet positioning reminder and planning system, characterized in that, include: The data acquisition module is used to collect user datasets, battery swapping cabinet datasets, and environmental datasets within the target service area, and to preprocess these datasets. The battery swapping demand forecasting module is used to comprehensively analyze the preprocessed user dataset and environmental dataset to obtain the battery swapping demand forecast value, and to evaluate the scale and distribution of battery swapping demand in each region within a preset time period based on the battery swapping demand forecast value. The battery health assessment module is used to comprehensively analyze the preprocessed battery swapping cabinet dataset, obtain battery health prediction values, and evaluate the current performance status of each battery in the battery swapping cabinet based on the battery health prediction values, and select healthy batteries that meet user needs. The load prediction module is used to comprehensively analyze the preprocessed battery swapping cabinet dataset and the predicted battery swapping demand to obtain the regional battery swapping cabinet load prediction value, and to evaluate the idle status and congestion risk of each battery swapping cabinet in the future preset time period based on the regional battery swapping cabinet load prediction value. The distance assessment module is used to comprehensively analyze the user location data in the preprocessed user dataset and the battery swapping cabinet location data in the preprocessed battery swapping cabinet dataset to obtain the distance assessment value, and to assess the convenience of users to reach each battery swapping cabinet based on the distance assessment value. The comprehensive recommendation module is used to perform correlation analysis on the preprocessed user dataset, battery swapping cabinet dataset, and environmental dataset to obtain scenario adaptation factors. It then performs comprehensive analysis on the scenario adaptation factors, battery swapping demand prediction values, battery health prediction values, regional battery swapping cabinet load prediction values, and distance assessment values ​​to obtain battery swapping cabinet recommendation assessment values. Based on the battery swapping cabinet recommendation assessment values, it selects the optimal battery swapping cabinet and alternative battery swapping cabinets from the battery swapping cabinets in each region.

2. The multi-area battery swapping cabinet positioning reminder and planning system according to claim 1, characterized in that: The user dataset includes user location data and user feature data. The user location data includes the user's real-time location coordinates, historical battery swapping location coordinates, and actual travel distance data from the current location to the battery swapping cabinets in various areas. The user feature data includes the user's vehicle model parameters, compatible battery model, current battery remaining power, and range requirements. The battery swapping cabinet dataset includes battery swapping cabinet location data, battery status data, and battery swapping cabinet operation data. The battery swapping cabinet location data includes the geographical coordinates of each battery swapping cabinet and its region information. The battery status data includes voltage time series data, temperature data, battery health, battery rated parameters, and battery charge / discharge cycle count. The battery swapping cabinet operation data includes battery reserve, real-time number of available bays, and real-time load of the battery swapping cabinet. The environmental dataset includes traffic data, which includes real-time congestion index and road travel time.

3. The multi-area battery swapping cabinet positioning reminder and planning system according to claim 1, characterized in that: The specific steps to obtain the predicted battery swapping demand are as follows: Extract historical battery swapping time, battery swapping potential, and battery swapping frequency data from the preprocessed user dataset, and combine them with historical battery swapping data from the same period in the corresponding time period. The extracted multi-dimensional data is correlated and matched in terms of time and space. Combined with the real-time occupancy status of the battery swapping cabinet, the occupancy adjustment coefficient is set. The battery swapping demand in areas with high occupancy is adjusted upward by the coefficient, and the battery swapping demand in areas with low occupancy is adjusted downward by the coefficient, thus forming a sample of regional battery swapping demand analysis. Based on the analysis of the sample, the influence trend of different dimensions of data on battery swapping demand is analyzed, and the predicted value of battery swapping demand in each region within a preset time period is obtained through multi-dimensional correlation analysis.

4. The multi-area battery swapping cabinet positioning reminder and planning system according to claim 1, characterized in that: The specific steps for assessing the scale and distribution of battery swapping demand in each region within a predetermined time period based on the predicted battery swapping demand are as follows: Set a threshold for the scale of battery swapping demand, compare the predicted value of battery swapping demand in each region with the threshold, and divide the region into high-demand, medium-demand, and low-demand areas. High-demand areas are marked as key areas of concern, and the priority of battery reserve allocation for battery swapping stations in these areas is increased. Medium-demand areas are allocated resources according to normal demand, and unnecessary battery replenishment is reduced in low-demand areas, with surplus batteries allocated to high-demand areas. By combining the spatial distribution data of the predicted battery swapping demand, a heat map of regional battery swapping demand is drawn to identify the concentration points of battery swapping demand in each sub-region.

5. The multi-area battery swapping cabinet positioning reminder and planning system according to claim 1, characterized in that: The specific steps to obtain the battery health prediction value are as follows: Extract voltage time-series data, temperature data, and battery rated parameters from the preprocessed battery swapping cabinet dataset; Analyze the correlation between voltage fluctuations, temperature changes, and current battery performance, and establish a battery performance evaluation model; Based on the model, a quantitative analysis of the current performance state of the battery is performed to obtain a predicted value for battery health.

6. The multi-area battery swapping cabinet positioning reminder and planning system according to claim 1, characterized in that: The specific steps for selecting healthy batteries that meet user needs are as follows: Extract users’ vehicle model and battery type range requirements from the preprocessed user dataset to determine users’ battery health and full-charge range requirements. The battery health prediction value is compared with the user's battery requirements to select batteries whose health and full-charge range meet the user's needs. The filtered batteries are sorted from highest to lowest health status, and the healthiest batteries in the highest ranking are matched with the user first.

7. The multi-area battery swapping cabinet positioning reminder and planning system according to claim 1, characterized in that: The specific steps to obtain the predicted load value of the battery swapping cabinet in the area are as follows: Extract the real-time load battery reserve data of the battery swapping cabinet from the preprocessed battery swapping cabinet dataset, and combine it with the predicted battery swapping demand to obtain the changing trend of battery swapping demand in the region. The study analyzes the changing pattern of real-time load of battery swapping cabinets with battery swapping demand, sets a congestion correction coefficient based on the number of real-time available slots, and analyzes the proportion of available slots and congestion warning time of each battery swapping cabinet in the future preset time period based on the coefficient. The congestion correction factor is used to correct the proportion of idle storage space and the congestion warning time. Then, the corrected proportion of idle storage space and the congestion warning time are integrated to obtain the predicted load value of the regional battery swapping cabinet.

8. The multi-area battery swapping cabinet positioning reminder and planning system according to claim 1, characterized in that: The specific steps to obtain the distance assessment value are as follows: Extract real-time user location coordinates from the preprocessed user dataset, and extract the geographic coordinates of each battery swapping cabinet from the preprocessed battery swapping cabinet dataset. Obtain the actual travel distance between the user's real-time location coordinates and the geographical coordinates of each battery swapping station, and at the same time, combine real-time traffic data to correct the travel time corresponding to the distance; The actual travel distance and travel time are quantified and converted to obtain a distance assessment value that represents the convenience of users to reach each battery swapping station.

9. A multi-area battery swapping cabinet positioning reminder and planning system according to claim 1, characterized in that: The specific steps to obtain the recommended evaluation value of the battery swapping cabinet are as follows: A correlation analysis was performed on the preprocessed user dataset, battery swapping cabinet dataset, and environmental dataset to obtain the scenario adaptation factors corresponding to each dimension of the data. By combining the scenario adaptation factor as a weighting coefficient with the predicted value of battery swapping demand, the predicted value of battery health, the predicted value of regional battery swapping cabinet load, and the distance assessment value, a comprehensive analysis is conducted to obtain the recommended assessment value of each battery swapping cabinet.

10. A method for positioning and planning multi-area battery swapping cabinets, used to implement the multi-area battery swapping cabinet positioning and planning system described in any one of claims 1-9, characterized in that: Includes the following steps: Step 1: Collect user datasets, battery swapping cabinet datasets, and environmental datasets within the target service area, and preprocess the user datasets, battery swapping cabinet datasets, and environmental datasets. Step 2: Conduct a comprehensive analysis of the preprocessed user dataset and environmental dataset to obtain the predicted value of battery swapping demand, and evaluate the scale and distribution of battery swapping demand in each region within the future preset time period based on the predicted value of battery swapping demand. Step 3: Perform a comprehensive analysis on the preprocessed battery swapping cabinet dataset to obtain battery health prediction values. Based on the battery health prediction values, evaluate the current performance status of each battery in the battery swapping cabinet and select healthy batteries that meet the user's needs. Step 4: Perform a comprehensive analysis on the preprocessed battery swapping cabinet dataset and the predicted battery swapping demand to obtain the predicted load value of the regional battery swapping cabinets, and assess the idle status and congestion risk of each battery swapping cabinet in the future preset time period based on the predicted load value of the regional battery swapping cabinets. Step 5: Perform a comprehensive analysis on the user location data in the preprocessed user dataset and the battery swapping cabinet location data in the preprocessed battery swapping cabinet dataset to obtain the distance evaluation value, and evaluate the convenience of users to reach each battery swapping cabinet based on the distance evaluation value. Step 6: Perform correlation analysis on the preprocessed user dataset, battery swapping cabinet dataset, and environmental dataset to obtain the scenario adaptation factor. Then, conduct a comprehensive analysis of the scenario adaptation factor with the predicted values ​​of battery swapping demand, battery health, regional battery swapping cabinet load, and distance assessment to obtain the recommended evaluation value of the battery swapping cabinet. Based on the recommended evaluation value, select the optimal battery swapping cabinet and the alternative battery swapping cabinet from the battery swapping cabinets in each region.

Images